{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 133363.920262817, "end_time": 136440.010917352, "total_evaluation_time_secondes": "3076.0906545349862", "model_name": "abhishek/autotrain-mixtral-8x7b-orpo-v1", "model_sha": "a8be37cf01ad767a0c71e0ba3af29c0b3ebcb559", "model_dtype": "torch.bfloat16", "model_size": "87.49 GB", "config": null }, "results": { "leaderboard|mmlu:abstract_algebra|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999 }, "leaderboard|mmlu:anatomy|5": { "acc": 0.6666666666666666, "acc_stderr": 0.04072314811876837 }, "leaderboard|mmlu:astronomy|5": { "acc": 0.7828947368421053, "acc_stderr": 0.03355045304882924 }, "leaderboard|mmlu:business_ethics|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237 }, "leaderboard|mmlu:clinical_knowledge|5": { "acc": 0.7358490566037735, "acc_stderr": 0.02713429162874171 }, "leaderboard|mmlu:college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388 }, "leaderboard|mmlu:college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795 }, "leaderboard|mmlu:college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633 }, "leaderboard|mmlu:college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235 }, "leaderboard|mmlu:college_medicine|5": { "acc": 0.6763005780346821, "acc_stderr": 0.0356760379963917 }, "leaderboard|mmlu:college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.049135952012744975 }, "leaderboard|mmlu:computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "leaderboard|mmlu:conceptual_physics|5": { "acc": 0.6340425531914894, "acc_stderr": 0.0314895582974553 }, "leaderboard|mmlu:econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.04598188057816543 }, "leaderboard|mmlu:electrical_engineering|5": { "acc": 0.6482758620689655, "acc_stderr": 0.039792366374974096 }, "leaderboard|mmlu:elementary_mathematics|5": { "acc": 0.46296296296296297, "acc_stderr": 0.025680564640056882 }, "leaderboard|mmlu:formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606 }, "leaderboard|mmlu:global_facts|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589 }, "leaderboard|mmlu:high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.021417242936321582 }, "leaderboard|mmlu:high_school_chemistry|5": { "acc": 0.5517241379310345, "acc_stderr": 0.034991131376767445 }, "leaderboard|mmlu:high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845 }, "leaderboard|mmlu:high_school_european_history|5": { "acc": 0.8, "acc_stderr": 0.031234752377721175 }, "leaderboard|mmlu:high_school_geography|5": { "acc": 0.8535353535353535, "acc_stderr": 0.025190921114603918 }, "leaderboard|mmlu:high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678185 }, "leaderboard|mmlu:high_school_macroeconomics|5": { "acc": 0.6923076923076923, "acc_stderr": 0.02340092891831049 }, "leaderboard|mmlu:high_school_mathematics|5": { "acc": 0.362962962962963, "acc_stderr": 0.02931820364520686 }, "leaderboard|mmlu:high_school_microeconomics|5": { "acc": 0.7521008403361344, "acc_stderr": 0.028047967224176896 }, "leaderboard|mmlu:high_school_physics|5": { "acc": 0.45695364238410596, "acc_stderr": 0.04067325174247443 }, "leaderboard|mmlu:high_school_psychology|5": { "acc": 0.8605504587155963, "acc_stderr": 0.014852421490033055 }, "leaderboard|mmlu:high_school_statistics|5": { "acc": 0.5555555555555556, "acc_stderr": 0.03388857118502325 }, "leaderboard|mmlu:high_school_us_history|5": { "acc": 0.8431372549019608, "acc_stderr": 0.025524722324553353 }, "leaderboard|mmlu:high_school_world_history|5": { "acc": 0.8565400843881856, "acc_stderr": 0.022818291821017012 }, "leaderboard|mmlu:human_aging|5": { "acc": 0.7533632286995515, "acc_stderr": 0.028930413120910884 }, "leaderboard|mmlu:human_sexuality|5": { "acc": 0.7709923664122137, "acc_stderr": 0.036853466317118506 }, "leaderboard|mmlu:international_law|5": { "acc": 0.8677685950413223, "acc_stderr": 0.030922788320445784 }, "leaderboard|mmlu:jurisprudence|5": { "acc": 0.7870370370370371, "acc_stderr": 0.0395783547198098 }, "leaderboard|mmlu:logical_fallacies|5": { "acc": 0.7791411042944786, "acc_stderr": 0.03259177392742178 }, "leaderboard|mmlu:machine_learning|5": { "acc": 0.5625, "acc_stderr": 0.04708567521880525 }, "leaderboard|mmlu:management|5": { "acc": 0.8349514563106796, "acc_stderr": 0.036756688322331886 }, "leaderboard|mmlu:marketing|5": { "acc": 0.9316239316239316, "acc_stderr": 0.01653462768431136 }, "leaderboard|mmlu:medical_genetics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282 }, "leaderboard|mmlu:miscellaneous|5": { "acc": 0.8467432950191571, "acc_stderr": 0.012881968968303275 }, "leaderboard|mmlu:moral_disputes|5": { "acc": 0.7254335260115607, "acc_stderr": 0.02402774515526502 }, "leaderboard|mmlu:moral_scenarios|5": { "acc": 0.45139664804469276, "acc_stderr": 0.01664330737231586 }, "leaderboard|mmlu:nutrition|5": { "acc": 0.7712418300653595, "acc_stderr": 0.024051029739912248 }, "leaderboard|mmlu:philosophy|5": { "acc": 0.729903536977492, "acc_stderr": 0.025218040373410633 }, "leaderboard|mmlu:prehistory|5": { "acc": 0.7932098765432098, "acc_stderr": 0.022535006705942835 }, "leaderboard|mmlu:professional_accounting|5": { "acc": 0.4929078014184397, "acc_stderr": 0.02982449855912901 }, "leaderboard|mmlu:professional_law|5": { "acc": 0.5039113428943938, "acc_stderr": 0.0127698453664412 }, "leaderboard|mmlu:professional_medicine|5": { "acc": 0.7536764705882353, "acc_stderr": 0.02617343857052 }, "leaderboard|mmlu:professional_psychology|5": { "acc": 0.36764705882352944, "acc_stderr": 0.019506291693954847 }, "leaderboard|mmlu:public_relations|5": { "acc": 0.6818181818181818, "acc_stderr": 0.04461272175910508 }, "leaderboard|mmlu:security_studies|5": { "acc": 0.7551020408163265, "acc_stderr": 0.027529637440174923 }, "leaderboard|mmlu:sociology|5": { "acc": 0.8507462686567164, "acc_stderr": 0.025196929874827058 }, "leaderboard|mmlu:us_foreign_policy|5": { "acc": 0.87, "acc_stderr": 0.03379976689896309 }, "leaderboard|mmlu:virology|5": { "acc": 0.5120481927710844, "acc_stderr": 0.03891364495835816 }, "leaderboard|mmlu:world_religions|5": { "acc": 0.8245614035087719, "acc_stderr": 0.02917088550072767 }, "leaderboard|mmlu:_average|5": { "acc": 0.6794451069040791, "acc_stderr": 0.03272737273781944 }, "all": { "acc": 0.6794451069040791, "acc_stderr": 0.03272737273781944 } }, "versions": { "leaderboard|mmlu:abstract_algebra|5": 0, "leaderboard|mmlu:anatomy|5": 0, "leaderboard|mmlu:astronomy|5": 0, "leaderboard|mmlu:business_ethics|5": 0, "leaderboard|mmlu:clinical_knowledge|5": 0, "leaderboard|mmlu:college_biology|5": 0, "leaderboard|mmlu:college_chemistry|5": 0, "leaderboard|mmlu:college_computer_science|5": 0, "leaderboard|mmlu:college_mathematics|5": 0, "leaderboard|mmlu:college_medicine|5": 0, "leaderboard|mmlu:college_physics|5": 0, "leaderboard|mmlu:computer_security|5": 0, "leaderboard|mmlu:conceptual_physics|5": 0, "leaderboard|mmlu:econometrics|5": 0, "leaderboard|mmlu:electrical_engineering|5": 0, "leaderboard|mmlu:elementary_mathematics|5": 0, "leaderboard|mmlu:formal_logic|5": 0, "leaderboard|mmlu:global_facts|5": 0, "leaderboard|mmlu:high_school_biology|5": 0, "leaderboard|mmlu:high_school_chemistry|5": 0, "leaderboard|mmlu:high_school_computer_science|5": 0, "leaderboard|mmlu:high_school_european_history|5": 0, "leaderboard|mmlu:high_school_geography|5": 0, "leaderboard|mmlu:high_school_government_and_politics|5": 0, "leaderboard|mmlu:high_school_macroeconomics|5": 0, "leaderboard|mmlu:high_school_mathematics|5": 0, "leaderboard|mmlu:high_school_microeconomics|5": 0, "leaderboard|mmlu:high_school_physics|5": 0, "leaderboard|mmlu:high_school_psychology|5": 0, "leaderboard|mmlu:high_school_statistics|5": 0, "leaderboard|mmlu:high_school_us_history|5": 0, "leaderboard|mmlu:high_school_world_history|5": 0, "leaderboard|mmlu:human_aging|5": 0, "leaderboard|mmlu:human_sexuality|5": 0, "leaderboard|mmlu:international_law|5": 0, "leaderboard|mmlu:jurisprudence|5": 0, "leaderboard|mmlu:logical_fallacies|5": 0, "leaderboard|mmlu:machine_learning|5": 0, "leaderboard|mmlu:management|5": 0, "leaderboard|mmlu:marketing|5": 0, "leaderboard|mmlu:medical_genetics|5": 0, "leaderboard|mmlu:miscellaneous|5": 0, "leaderboard|mmlu:moral_disputes|5": 0, "leaderboard|mmlu:moral_scenarios|5": 0, "leaderboard|mmlu:nutrition|5": 0, "leaderboard|mmlu:philosophy|5": 0, "leaderboard|mmlu:prehistory|5": 0, "leaderboard|mmlu:professional_accounting|5": 0, "leaderboard|mmlu:professional_law|5": 0, "leaderboard|mmlu:professional_medicine|5": 0, "leaderboard|mmlu:professional_psychology|5": 0, "leaderboard|mmlu:public_relations|5": 0, "leaderboard|mmlu:security_studies|5": 0, "leaderboard|mmlu:sociology|5": 0, "leaderboard|mmlu:us_foreign_policy|5": 0, "leaderboard|mmlu:virology|5": 0, "leaderboard|mmlu:world_religions|5": 0 }, "config_tasks": { "leaderboard|mmlu:abstract_algebra": { "name": "mmlu:abstract_algebra", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "abstract_algebra", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:anatomy": { "name": "mmlu:anatomy", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "anatomy", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 135, "effective_num_docs": 135, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:astronomy": { "name": "mmlu:astronomy", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "astronomy", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 152, "effective_num_docs": 152, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:business_ethics": { "name": "mmlu:business_ethics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "business_ethics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:clinical_knowledge": { "name": "mmlu:clinical_knowledge", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "clinical_knowledge", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 265, "effective_num_docs": 265, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_biology": { "name": "mmlu:college_biology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_biology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 144, "effective_num_docs": 144, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_chemistry": { "name": "mmlu:college_chemistry", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_chemistry", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_computer_science": { "name": "mmlu:college_computer_science", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_computer_science", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_mathematics": { "name": "mmlu:college_mathematics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_mathematics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_medicine": { "name": "mmlu:college_medicine", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_medicine", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 173, "effective_num_docs": 173, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:college_physics": { "name": "mmlu:college_physics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "college_physics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 102, "effective_num_docs": 102, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:computer_security": { "name": "mmlu:computer_security", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "computer_security", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:conceptual_physics": { "name": "mmlu:conceptual_physics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "conceptual_physics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 235, "effective_num_docs": 235, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:econometrics": { "name": "mmlu:econometrics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "econometrics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 114, "effective_num_docs": 114, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:electrical_engineering": { "name": "mmlu:electrical_engineering", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "electrical_engineering", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 145, "effective_num_docs": 145, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:elementary_mathematics": { "name": "mmlu:elementary_mathematics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "elementary_mathematics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 378, "effective_num_docs": 378, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:formal_logic": { "name": "mmlu:formal_logic", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "formal_logic", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 126, "effective_num_docs": 126, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:global_facts": { "name": "mmlu:global_facts", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "global_facts", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_biology": { "name": "mmlu:high_school_biology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_biology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 310, "effective_num_docs": 310, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_chemistry": { "name": "mmlu:high_school_chemistry", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_chemistry", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 203, "effective_num_docs": 203, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_computer_science": { "name": "mmlu:high_school_computer_science", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_computer_science", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_european_history": { "name": "mmlu:high_school_european_history", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_european_history", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 165, "effective_num_docs": 165, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_geography": { "name": "mmlu:high_school_geography", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_geography", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 198, "effective_num_docs": 198, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_government_and_politics": { "name": "mmlu:high_school_government_and_politics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_government_and_politics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 193, "effective_num_docs": 193, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_macroeconomics": { "name": "mmlu:high_school_macroeconomics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_macroeconomics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 390, "effective_num_docs": 390, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_mathematics": { "name": "mmlu:high_school_mathematics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_mathematics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 270, "effective_num_docs": 270, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_microeconomics": { "name": "mmlu:high_school_microeconomics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_microeconomics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 238, "effective_num_docs": 238, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_physics": { "name": "mmlu:high_school_physics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_physics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 151, "effective_num_docs": 151, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_psychology": { "name": "mmlu:high_school_psychology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_psychology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 545, "effective_num_docs": 545, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_statistics": { "name": "mmlu:high_school_statistics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_statistics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 216, "effective_num_docs": 216, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_us_history": { "name": "mmlu:high_school_us_history", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_us_history", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 204, "effective_num_docs": 204, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:high_school_world_history": { "name": "mmlu:high_school_world_history", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "high_school_world_history", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 237, "effective_num_docs": 237, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:human_aging": { "name": "mmlu:human_aging", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "human_aging", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 223, "effective_num_docs": 223, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:human_sexuality": { "name": "mmlu:human_sexuality", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "human_sexuality", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 131, "effective_num_docs": 131, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:international_law": { "name": "mmlu:international_law", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "international_law", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 121, "effective_num_docs": 121, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:jurisprudence": { "name": "mmlu:jurisprudence", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "jurisprudence", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 108, "effective_num_docs": 108, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:logical_fallacies": { "name": "mmlu:logical_fallacies", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "logical_fallacies", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 163, "effective_num_docs": 163, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:machine_learning": { "name": "mmlu:machine_learning", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "machine_learning", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 112, "effective_num_docs": 112, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:management": { "name": "mmlu:management", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "management", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 103, "effective_num_docs": 103, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:marketing": { "name": "mmlu:marketing", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "marketing", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 234, "effective_num_docs": 234, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:medical_genetics": { "name": "mmlu:medical_genetics", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "medical_genetics", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:miscellaneous": { "name": "mmlu:miscellaneous", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "miscellaneous", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 783, "effective_num_docs": 783, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:moral_disputes": { "name": "mmlu:moral_disputes", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "moral_disputes", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 346, "effective_num_docs": 346, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:moral_scenarios": { "name": "mmlu:moral_scenarios", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "moral_scenarios", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 895, "effective_num_docs": 895, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:nutrition": { "name": "mmlu:nutrition", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "nutrition", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 306, "effective_num_docs": 306, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:philosophy": { "name": "mmlu:philosophy", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "philosophy", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 311, "effective_num_docs": 311, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:prehistory": { "name": "mmlu:prehistory", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "prehistory", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 324, "effective_num_docs": 324, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:professional_accounting": { "name": "mmlu:professional_accounting", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "professional_accounting", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 282, "effective_num_docs": 282, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:professional_law": { "name": "mmlu:professional_law", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "professional_law", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 1534, "effective_num_docs": 1534, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:professional_medicine": { "name": "mmlu:professional_medicine", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "professional_medicine", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 272, "effective_num_docs": 272, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:professional_psychology": { "name": "mmlu:professional_psychology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "professional_psychology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 612, "effective_num_docs": 612, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:public_relations": { "name": "mmlu:public_relations", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "public_relations", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 110, "effective_num_docs": 110, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:security_studies": { "name": "mmlu:security_studies", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "security_studies", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 245, "effective_num_docs": 245, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:sociology": { "name": "mmlu:sociology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "sociology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 201, "effective_num_docs": 201, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:us_foreign_policy": { "name": "mmlu:us_foreign_policy", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "us_foreign_policy", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 100, "effective_num_docs": 100, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:virology": { "name": "mmlu:virology", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "virology", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 166, "effective_num_docs": 166, "trust_dataset": true, "must_remove_duplicate_docs": null }, "leaderboard|mmlu:world_religions": { "name": "mmlu:world_religions", "prompt_function": "mmlu_harness", "hf_repo": "lighteval/mmlu", "hf_subset": "world_religions", "metric": [ "loglikelihood_acc" ], "hf_avail_splits": [ "auxiliary_train", "test", "validation", "dev" ], "evaluation_splits": [ "test" ], "few_shots_split": "dev", "few_shots_select": "sequential", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard", "mmlu" ], "original_num_docs": 171, "effective_num_docs": 171, "trust_dataset": true, "must_remove_duplicate_docs": null } }, "summary_tasks": { "leaderboard|mmlu:abstract_algebra|5": { "hashes": { "hash_examples": "4c76229e00c9c0e9", "hash_full_prompts": "a45d01c3409c889c", "hash_input_tokens": "0fe5779bbfd39458", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:anatomy|5": { "hashes": { "hash_examples": "6a1f8104dccbd33b", "hash_full_prompts": "e245c6600e03cc32", "hash_input_tokens": "6985602b3df0fdf2", "hash_cont_tokens": "4020fc250ba8855e" }, "truncated": 0, "non_truncated": 135, "padded": 540, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:astronomy|5": { "hashes": { "hash_examples": "1302effa3a76ce4c", "hash_full_prompts": "390f9bddf857ad04", "hash_input_tokens": "9f47aa4a827f09ca", "hash_cont_tokens": "2e19ba0f9d464ec7" }, "truncated": 0, "non_truncated": 152, "padded": 608, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:business_ethics|5": { "hashes": { "hash_examples": "03cb8bce5336419a", "hash_full_prompts": "5504f893bc4f2fa1", "hash_input_tokens": "be1ff3eeae3168ca", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:clinical_knowledge|5": { "hashes": { "hash_examples": "ffbb9c7b2be257f9", "hash_full_prompts": "106ad0bab4b90b78", "hash_input_tokens": "281e8a4124636628", "hash_cont_tokens": "6e942fe2858712ae" }, "truncated": 0, "non_truncated": 265, "padded": 1060, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_biology|5": { "hashes": { "hash_examples": "3ee77f176f38eb8e", "hash_full_prompts": "59f9bdf2695cb226", "hash_input_tokens": "5f1c618e37182983", "hash_cont_tokens": "750cf0dfeff046c4" }, "truncated": 0, "non_truncated": 144, "padded": 576, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_chemistry|5": { "hashes": { "hash_examples": "ce61a69c46d47aeb", "hash_full_prompts": "3cac9b759fcff7a0", "hash_input_tokens": "7716b78a5b2c7766", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_computer_science|5": { "hashes": { "hash_examples": "32805b52d7d5daab", "hash_full_prompts": "010b0cca35070130", "hash_input_tokens": "2eaf06d29b70feec", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_mathematics|5": { "hashes": { "hash_examples": "55da1a0a0bd33722", "hash_full_prompts": "511422eb9eefc773", "hash_input_tokens": "2e9212af94cf016b", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_medicine|5": { "hashes": { "hash_examples": "c33e143163049176", "hash_full_prompts": "c8cc1a82a51a046e", "hash_input_tokens": "1cf3bd162e71ec93", "hash_cont_tokens": "de458bd9f6f4c1e8" }, "truncated": 0, "non_truncated": 173, "padded": 692, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:college_physics|5": { "hashes": { "hash_examples": "ebdab1cdb7e555df", "hash_full_prompts": "e40721b5059c5818", "hash_input_tokens": "8a3b0f963fd18269", "hash_cont_tokens": "3ec87f548a37bddc" }, "truncated": 0, "non_truncated": 102, "padded": 408, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:computer_security|5": { "hashes": { "hash_examples": "a24fd7d08a560921", "hash_full_prompts": "946c9be5964ac44a", "hash_input_tokens": "4d527e954909d404", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:conceptual_physics|5": { "hashes": { "hash_examples": "8300977a79386993", "hash_full_prompts": "506a4f6094cc40c9", "hash_input_tokens": "78097767b921e219", "hash_cont_tokens": "13d792c5220dc0e8" }, "truncated": 0, "non_truncated": 235, "padded": 940, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:econometrics|5": { "hashes": { "hash_examples": "ddde36788a04a46f", "hash_full_prompts": "4ed2703f27f1ed05", "hash_input_tokens": "75170aedf177c885", "hash_cont_tokens": "5cd59218b163ddfd" }, "truncated": 0, "non_truncated": 114, "padded": 456, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:electrical_engineering|5": { "hashes": { "hash_examples": "acbc5def98c19b3f", "hash_full_prompts": "d8f4b3e11c23653c", "hash_input_tokens": "62f8d9c4ee3b4ba3", "hash_cont_tokens": "9287b3a50a11bdba" }, "truncated": 0, "non_truncated": 145, "padded": 580, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:elementary_mathematics|5": { "hashes": { "hash_examples": "146e61d07497a9bd", "hash_full_prompts": "256d111bd15647ff", "hash_input_tokens": "0ec6d03f7194631b", "hash_cont_tokens": "23a8931ce3aa84c9" }, "truncated": 0, "non_truncated": 378, "padded": 1512, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:formal_logic|5": { "hashes": { "hash_examples": "8635216e1909a03f", "hash_full_prompts": "1171d04f3b1a11f5", "hash_input_tokens": "73487a28bc4960a8", "hash_cont_tokens": "d3b0643c11a8cc1b" }, "truncated": 0, "non_truncated": 126, "padded": 504, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:global_facts|5": { "hashes": { "hash_examples": "30b315aa6353ee47", "hash_full_prompts": "a7e56dbc074c7529", "hash_input_tokens": "388c66d3a197fa0a", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_biology|5": { "hashes": { "hash_examples": "c9136373af2180de", "hash_full_prompts": "ad6e859ed978e04a", "hash_input_tokens": "9a7dcf6401f12c9a", "hash_cont_tokens": "9d90477d239cc6d8" }, "truncated": 0, "non_truncated": 310, "padded": 1240, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_chemistry|5": { "hashes": { "hash_examples": "b0661bfa1add6404", "hash_full_prompts": "6eb9c04bcc8a8f2a", "hash_input_tokens": "95a5f5cb0ad4ae51", "hash_cont_tokens": "d518689c1577a5bb" }, "truncated": 0, "non_truncated": 203, "padded": 812, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_computer_science|5": { "hashes": { "hash_examples": "80fc1d623a3d665f", "hash_full_prompts": "8e51bc91c81cf8dd", "hash_input_tokens": "334bb7ac1e7f058c", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_european_history|5": { "hashes": { "hash_examples": "854da6e5af0fe1a1", "hash_full_prompts": "664a1f16c9f3195c", "hash_input_tokens": "fe5ac2f30a47b01e", "hash_cont_tokens": "f27fd41b64bb6c6d" }, "truncated": 0, "non_truncated": 165, "padded": 656, "non_padded": 4, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_geography|5": { "hashes": { "hash_examples": "7dc963c7acd19ad8", "hash_full_prompts": "f3acf911f4023c8a", "hash_input_tokens": "dbb8fb6fa1921225", "hash_cont_tokens": "88bb0ab56be2e694" }, "truncated": 0, "non_truncated": 198, "padded": 792, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_government_and_politics|5": { "hashes": { "hash_examples": "1f675dcdebc9758f", "hash_full_prompts": "066254feaa3158ae", "hash_input_tokens": "b5cd164a3689a010", "hash_cont_tokens": "f6854f1bb4b558c1" }, "truncated": 0, "non_truncated": 193, "padded": 772, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_macroeconomics|5": { "hashes": { "hash_examples": "2fb32cf2d80f0b35", "hash_full_prompts": "19a7fa502aa85c95", "hash_input_tokens": "e5af1d29ec1375ef", "hash_cont_tokens": "6c8e0dc09bb99e37" }, "truncated": 0, "non_truncated": 390, "padded": 1560, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_mathematics|5": { "hashes": { "hash_examples": "fd6646fdb5d58a1f", "hash_full_prompts": "4f704e369778b5b0", "hash_input_tokens": "6a77d1eeaaa13f88", "hash_cont_tokens": "6feef2732c1b2d4c" }, "truncated": 0, "non_truncated": 270, "padded": 1080, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_microeconomics|5": { "hashes": { "hash_examples": "2118f21f71d87d84", "hash_full_prompts": "4350f9e2240f8010", "hash_input_tokens": "df8ba3a19ec61286", "hash_cont_tokens": "f9dfc942b16f5267" }, "truncated": 0, "non_truncated": 238, "padded": 949, "non_padded": 3, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_physics|5": { "hashes": { "hash_examples": "dc3ce06378548565", "hash_full_prompts": "5dc0d6831b66188f", "hash_input_tokens": "c2f89913d26b3804", "hash_cont_tokens": "c9b6fb68f1119c6c" }, "truncated": 0, "non_truncated": 151, "padded": 604, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_psychology|5": { "hashes": { "hash_examples": "c8d1d98a40e11f2f", "hash_full_prompts": "af2b097da6d50365", "hash_input_tokens": "fca84bcc94a0f457", "hash_cont_tokens": "5024b2446e7f0d51" }, "truncated": 0, "non_truncated": 545, "padded": 2178, "non_padded": 2, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_statistics|5": { "hashes": { "hash_examples": "666c8759b98ee4ff", "hash_full_prompts": "c757694421d6d68d", "hash_input_tokens": "8f6a5c418a13d2fb", "hash_cont_tokens": "2bb63458482cea04" }, "truncated": 0, "non_truncated": 216, "padded": 864, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_us_history|5": { "hashes": { "hash_examples": "95fef1c4b7d3f81e", "hash_full_prompts": "e34a028d0ddeec5e", "hash_input_tokens": "6668b57a661aafc5", "hash_cont_tokens": "5666f3f217d4332c" }, "truncated": 0, "non_truncated": 204, "padded": 816, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:high_school_world_history|5": { "hashes": { "hash_examples": "7e5085b6184b0322", "hash_full_prompts": "1fa3d51392765601", "hash_input_tokens": "73aeb6bb3ae4d1e9", "hash_cont_tokens": "dd7e50c17b54c08f" }, "truncated": 0, "non_truncated": 237, "padded": 948, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:human_aging|5": { "hashes": { "hash_examples": "c17333e7c7c10797", "hash_full_prompts": "cac900721f9a1a94", "hash_input_tokens": "b03c5226fb519d7a", "hash_cont_tokens": "66bb7b523dbd018d" }, "truncated": 0, "non_truncated": 223, "padded": 892, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:human_sexuality|5": { "hashes": { "hash_examples": "4edd1e9045df5e3d", "hash_full_prompts": "0d6567bafee0a13c", "hash_input_tokens": "062d0f125fea9343", "hash_cont_tokens": "9c12fbd8915b29d8" }, "truncated": 0, "non_truncated": 131, "padded": 524, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:international_law|5": { "hashes": { "hash_examples": "db2fa00d771a062a", "hash_full_prompts": "d018f9116479795e", "hash_input_tokens": "af37ce0e58de6237", "hash_cont_tokens": "939bc6141fbc2edf" }, "truncated": 0, "non_truncated": 121, "padded": 484, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:jurisprudence|5": { "hashes": { "hash_examples": "e956f86b124076fe", "hash_full_prompts": "1487e89a10ec58b7", "hash_input_tokens": "49b4ea770c987d32", "hash_cont_tokens": "0ec098526f036a8a" }, "truncated": 0, "non_truncated": 108, "padded": 424, "non_padded": 8, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:logical_fallacies|5": { "hashes": { "hash_examples": "956e0e6365ab79f1", "hash_full_prompts": "677785b2181f9243", "hash_input_tokens": "dd09600885a64129", "hash_cont_tokens": "22cadb0152a35b33" }, "truncated": 0, "non_truncated": 163, "padded": 632, "non_padded": 20, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:machine_learning|5": { "hashes": { "hash_examples": "397997cc6f4d581e", "hash_full_prompts": "769ee14a2aea49bb", "hash_input_tokens": "de15e01f132712a1", "hash_cont_tokens": "ba0c03916a4f8962" }, "truncated": 0, "non_truncated": 112, "padded": 448, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:management|5": { "hashes": { "hash_examples": "2bcbe6f6ca63d740", "hash_full_prompts": "cb1ff9dac9582144", "hash_input_tokens": "0bdd13c3e253c084", "hash_cont_tokens": "a0189ce8f55ad1bc" }, "truncated": 0, "non_truncated": 103, "padded": 412, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:marketing|5": { "hashes": { "hash_examples": "8ddb20d964a1b065", "hash_full_prompts": "9fc2114a187ad9a2", "hash_input_tokens": "11542dea73278c57", "hash_cont_tokens": "7c475ce17ba7f995" }, "truncated": 0, "non_truncated": 234, "padded": 916, "non_padded": 20, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:medical_genetics|5": { "hashes": { "hash_examples": "182a71f4763d2cea", "hash_full_prompts": "46a616fa51878959", "hash_input_tokens": "d2cbccb05c894c9a", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:miscellaneous|5": { "hashes": { "hash_examples": "4c404fdbb4ca57fc", "hash_full_prompts": "0813e1be36dbaae1", "hash_input_tokens": "dc43c11c1d22c9cc", "hash_cont_tokens": "fffaa9d5e21ea2af" }, "truncated": 0, "non_truncated": 783, "padded": 3128, "non_padded": 4, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:moral_disputes|5": { "hashes": { "hash_examples": "60cbd2baa3fea5c9", "hash_full_prompts": "1d14adebb9b62519", "hash_input_tokens": "e14bc256c0636235", "hash_cont_tokens": "7148539bc2747f6f" }, "truncated": 0, "non_truncated": 346, "padded": 1380, "non_padded": 4, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:moral_scenarios|5": { "hashes": { "hash_examples": "fd8b0431fbdd75ef", "hash_full_prompts": "b80d3d236165e3de", "hash_input_tokens": "3ad51653e199ecb5", "hash_cont_tokens": "ab3904f2ea05d117" }, "truncated": 0, "non_truncated": 895, "padded": 3575, "non_padded": 5, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:nutrition|5": { "hashes": { "hash_examples": "71e55e2b829b6528", "hash_full_prompts": "2bfb18e5fab8dea7", "hash_input_tokens": "9fc73099308228de", "hash_cont_tokens": "77b06e0a3882a218" }, "truncated": 0, "non_truncated": 306, "padded": 1224, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:philosophy|5": { "hashes": { "hash_examples": "a6d489a8d208fa4b", "hash_full_prompts": "e8c0d5b6dae3ccc8", "hash_input_tokens": "1f04529a01331877", "hash_cont_tokens": "16547f8767db6b33" }, "truncated": 0, "non_truncated": 311, "padded": 1244, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:prehistory|5": { "hashes": { "hash_examples": "6cc50f032a19acaa", "hash_full_prompts": "4a6a1d3ab1bf28e4", "hash_input_tokens": "b888c315b2fe260f", "hash_cont_tokens": "d02c802ddda38fc6" }, "truncated": 0, "non_truncated": 324, "padded": 1280, "non_padded": 16, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:professional_accounting|5": { "hashes": { "hash_examples": "50f57ab32f5f6cea", "hash_full_prompts": "e60129bd2d82ffc6", "hash_input_tokens": "f7d95500add349b4", "hash_cont_tokens": "727a930b413e9dcc" }, "truncated": 0, "non_truncated": 282, "padded": 1112, "non_padded": 16, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:professional_law|5": { "hashes": { "hash_examples": "a8fdc85c64f4b215", "hash_full_prompts": "0dbb1d9b72dcea03", "hash_input_tokens": "118dc3fd9f9a3ee4", "hash_cont_tokens": "a6b7566ed4e357a4" }, "truncated": 0, "non_truncated": 1534, "padded": 6136, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:professional_medicine|5": { "hashes": { "hash_examples": "c373a28a3050a73a", "hash_full_prompts": "5e040f9ca68b089e", "hash_input_tokens": "a05e408a696a471a", "hash_cont_tokens": "842eee9669bb319c" }, "truncated": 0, "non_truncated": 272, "padded": 1088, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:professional_psychology|5": { "hashes": { "hash_examples": "bf5254fe818356af", "hash_full_prompts": "b386ecda8b87150e", "hash_input_tokens": "24311c9a35d0d28e", "hash_cont_tokens": "be012eab9f44677d" }, "truncated": 0, "non_truncated": 612, "padded": 2448, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:public_relations|5": { "hashes": { "hash_examples": "b66d52e28e7d14e0", "hash_full_prompts": "fe43562263e25677", "hash_input_tokens": "3423b8f3b48e9623", "hash_cont_tokens": "94f3463ddfbff82d" }, "truncated": 0, "non_truncated": 110, "padded": 436, "non_padded": 4, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:security_studies|5": { "hashes": { "hash_examples": "514c14feaf000ad9", "hash_full_prompts": "27d4a2ac541ef4b9", "hash_input_tokens": "fda6731d7b1ee470", "hash_cont_tokens": "8a9a00a3be4137d7" }, "truncated": 0, "non_truncated": 245, "padded": 980, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:sociology|5": { "hashes": { "hash_examples": "f6c9bc9d18c80870", "hash_full_prompts": "c072ea7d1a1524f2", "hash_input_tokens": "9dc8c12d6e111a44", "hash_cont_tokens": "b342c9aa0cc9576f" }, "truncated": 0, "non_truncated": 201, "padded": 804, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:us_foreign_policy|5": { "hashes": { "hash_examples": "ed7b78629db6678f", "hash_full_prompts": "341a97ca3e4d699d", "hash_input_tokens": "c5eaba656a6b29de", "hash_cont_tokens": "5739133e99fb8ad8" }, "truncated": 0, "non_truncated": 100, "padded": 400, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:virology|5": { "hashes": { "hash_examples": "bc52ffdc3f9b994a", "hash_full_prompts": "651d471e2eb8b5e9", "hash_input_tokens": "46fe9c766d7e8ace", "hash_cont_tokens": "81e5cec1153bffc8" }, "truncated": 0, "non_truncated": 166, "padded": 664, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "leaderboard|mmlu:world_religions|5": { "hashes": { "hash_examples": "ecdb4a4f94f62930", "hash_full_prompts": "3773f03542ce44a3", "hash_input_tokens": "1010d6d65948506f", "hash_cont_tokens": "1d7b5eb727cbc4c6" }, "truncated": 0, "non_truncated": 171, "padded": 684, "non_padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "341a076d0beb7048", "hash_full_prompts": "a5c8f2b7ff4f5ae2", "hash_input_tokens": "b5af86d667921a83", "hash_cont_tokens": "02ae1fe9bf3431a5" }, "truncated": 0, "non_truncated": 14042, "padded": 56062, "non_padded": 106, "num_truncated_few_shots": 0 } }